DOCSLIB.ORG

Evaluating the Case for Regulation of Digital Platforms Giuseppe Colangelo*

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Evaluating the Case for Regulation of Digital Platforms Giuseppe Colangelo* Evaluating the Case for Regulation of Digital Platforms Giuseppe Colangelo* INTRODUCTION: THE CRISIS OF ANTITRUST IN THE DIGITAL ECONOMY Antitrust enforcement and competition policy in the digital economy is high on the agenda of authorities and policymakers. The flood of reports and policy papers recently released reflects the ongoing debate over the capability of current antitrust rules and tools to handle the emergence of large technology platforms (BigTechs) and to scrutinize their practices and business models. The distinctive features of digital markets apparently require a rethinking of the antitrust regime. The presence of strong economies of scale, extreme indirect network effects, remarkable economies of scope due the role of data as a critical input, and conglomerate effects, along with consumers’ behavioural biases and single-homing tendencies, represent significant barriers to entry that make digital markets highly concentrated, prone to tipping, and not easily contestable. Therefore, large incumbent players appear not to be under threat and hard to dislodge. Moreover, digital platforms act as gatekeepers (either by controlling the access of third-party firms to their users or controlling the consumption of products and services by their users) and regulators (due to their rule-setting role within their ecosystem), and frequently play a dual role, being simultaneously operators for the marketplace and sellers of their own products and services in competition with rival sellers. In light of this, mounting criticism against current competition policy allege that lax antitrust enforcement, flawed Judicial rules that reflect unsound economic theories or unsupported empirical claims, and the limited effectiveness of the antitrust toolkit have * Jean Monet Professor of EU Innovation Policy; Associate Professor of Law and Economics, University of Basilicata; TTLF Fellow, Stanford University and University of Vienna; giuseppe.colangelo1975 @gmail.com. The GAI Report on the Digital Economy contributed to a significant increase in concentration in digital markets.1 Furthermore, antitrust litigation and enforcement are deemed to be too protracted and expensive, causing ambiguity, draining resources, and privileging incumbents.2 Despite the Department of Justice’s Antitrust Division (DOJ) ongoing reviewing of whether and how certain online platforms have achieved market power and are engaging in anti- competitive practices3 and the Federal Trade Commission’s (FTC) launching of an ex post evaluation of BigTech acquisitions,4 there is strong scepticism and criticism surrounding the efficacy of antitrust investigations. Too little, too late. By this view, the only cure to the antitrust crisis is to implement a wave of regulatory reforms. Despite concerns about the effective implementation of reform proposals aimed at providing greater control of BigTechs’ practices,5 and doubts about 1 AMERICAN ANTITRUST INSTITUTE, THE STATE OF ANTITRUST ENFORCEMENT AND COMPETITION POLICY IN THE U.S. (2020); Joint Response to the House Judiciary Committee, Antitrust Experts for the Washington Center for Equitable Growth, State of Antitrust Law and Implications for Protecting Competition in Digital Markets (April 30, 2020), https://equitablegrowth.org/wp-content/uploads/2020/04/Joint-Response-to-the- House-Judiciary-Committee-on-the-State-of-Antitrust-Law-and-Implications-for-Protecting-Competition- in-Digital-Markets.pdf; U.S. HOUSE OF REPRESENTATIVES, SUBCOMMITTEE ON ANTITRUST, COMMERCIAL, AND ADMINISTRATIVE LAW, INVESTIGATION OF COMPETITION IN DIGITAL MARKETS, MAJORITY STAFF REPORTS AND RECOMMENDATIONS (October 2020)[hereinafter HOUSE OF REPRESENTATIVES REPORT]. See also Carl Shapiro, Protecting Competition in the American Economy: Merger Control, Tech Titans, Labor Markets, 33 J. ECON. PERSP. 69 (2019) (urging to reinvigorate antitrust enforcement in the U.S. in three areas, e.g., merger control, the treatment of exclusionary conduct by dominant firms, and the market power of employers as buyers in labor markets); Spencer Weber Waller, Submission to the U.S. House Judiciary Antitrust Subcommittee Investigation of Digital Platforms (April 28 2020), https://papers.ssrn.com/sol3/papers .cfm?abstract_id=3567376 (arguing that the U.S. has become “a laggard, and not a leader” in the formulation of global competition policy). 2 Rohit Chopra & Lina M. Khan, The Case for “Unfair Methods of Competition” Rulemaking, 87 UNIV. CHI. L. REV. 357, 368 (2020). 3 U.S. DEPARTMENT OF JUSTICE, JUSTICE DEPARTMENT REVIEWING THE PRACTICES OF MARKET-LEADING ONLINE PLATFORMS (2019). 4 U.S. FEDERAL TRADE COMMISSION, FTC TO EXAMINE PAST ACQUISITIONS BY LARGE TECHNOLOGY COMPANIES (2020). 5 Alison Jones & William E. Kovacic, Antitrust’s Implementation Blind Side: Challenges to Major Expansion of U.S. Competition Policy, ANTITRUST BULLETIN (forthcoming 2020). See also U.S. COUNCIL OF ECONOMIC ADVISERS, ECONOMIC REPORT OF THE PRESIDENT 22 (2020). 906 Colangelo – Evaluating the Case for Regulation of Digital Platforms the nostalgia for past adventures,6 and even despite the common understanding reached by G7 competition authorities in June 2019—i.e. challenging issues raised by digital markets are not beyond the reach of antitrust law and many of the features of digital markets can be successfully addressed with existing toolkits since antitrust ensures a flexible framework and a fact-based, cross-sectoral and technology-neutral analysis7— regulation is back on the table for policy discussions. Quite surprisingly, it is also on the minds of members of the mainstream antitrust communities.8 Notably, some proposals envisage a public utilities-style regulation for the digital economy, advocating the creation of a digital authority able to impose measures against companies that have a strategic market status.9 Some proponents go even further by suggesting break-ups and bans on vertical integration altogether in order to address economic and social concerns arising from BigTechs.10 Other reform proposals point to 6 Christine S. Wilson & Keith Klovers, The Growing Nostalgia for Past Regulatory Misadventures and the Risk of Repeating These Mistakes with Big Tech, 8 J. ANTITRUST ENF’T 10 (2020). See also Jean Tirole, Competition and the Industrial Challenge for the Digital Age, (unpublished manuscript) (April 3, 2020) (considering old-style regulation impractical in an era of global firms, rapid technological progress and contestable markets) https://www.tse- fr.eu/sites/default/files/TSE/documents/doc/by/tirole/competition_and_the_industrial_challenge_april_3_ 2020.pdf. 7 G7 COMPETITION AUTHORITIES, COMMON UNDERSTANDING ON COMPETITION AND THE DIGITAL ECONOMY (2019). 8 A. Douglas Melamed, Antitrust Law and its Critics, 83 ANTITRUST L. J. (forthcoming 2020). 9 STIGLER COMMITTEE FOR THE STUDY OF DIGITAL PLATFORMS, MARKET STRUCTURE AND ANTITRUST SUBCOMMITTEE (2019); UK COMPETITION AND MARKETS AUTHORITY, Online Platforms and Digital Advertising, in MARKET STUDY REPORT (2020; UK DIGITAL COMPETITION EXPERT PANEL, Unlocking digital competition, in REPORT OF THE DIGITAL COMPETITION EXPERT PANEL (March 2019). 10 Lina M. Khan, The Separation of Platforms and Commerce, 119 COLUM. L. REV. 973 (2019); Open Markets Institute, Restoring Antimonopoly Through Bright-Line Rules, OPEN MARKETS (April 26, 2019), https://openmarketsinstitute.org/op-eds-and-articles/restoring-antimonopoly-bright-line-rules/; K. Sabeel Rahman, Regulating informational infrastructure: Internet Platforms as the New Public Utilities, 2 GEO. L. TECH. REV. 234 (2018); Matt Stoller, Sarah Miller, & Zephir Teachout, Addressing Facebook and Google’s Harms Through a Regulated Competition Approach (Am. Econ. Liberties Project, Working Paper No. 2, 2020), https://static1.squarespace.com/static/5df44e0792ff6a63789b5c02/t/5e90c1f1f177386f95c33662/15865451395 29/Working+Paper+Series+on+Corporate+Power_2.pdf; JONATHAN TAPLIN, MOVE FAST AND BREAK THINGS: HOW FACEBOOK, GOOGLE, AND AMAZON CORNERED CULTURE AND UNDERMINED DEMOCRACY (2019); U.S. HOUSE OF REPRESENTATIVES REPORT, supra note 1, at 380; Rory Van Loo, In Defense of Breakups: Administering 907 The GAI Report on the Digital Economy the need to integrate the antitrust toolkit with ex ante prohibitions to prevent anti- competitive practices by dominant platforms, since, according to this view, there is a risk that ex post enforcement would be too slow to successfully keep markets competitive and contestable in fast-moving markets characterized by a winner-takes-most dynamic.11 Although the proposed solutions might diverge and reflect a heavy regulatory approach to antitrust law rather than the traditional paradigm of economics-based regulation,12 all the proposals question the role of antitrust in the digital economy and some suggest that online platforms should be treated as common carriers.13 The aim of this chapter is to analyze recently released reports and policy papers to evaluate whether regulatory interventions reflect the distinctive features of digital markets and their leading players or whether the main thrust of these proposals for regulatory interventions is Just to circumvent the burdens imposed by standard antitrust a 'Radical' Remedy, CORNELL L. REV. (forthcoming 2020); TIM WU, THE CURSE OF BIGNESS: ANTITRUST IN THE NEW GILDED AGE (2018). 11 European Commission, Proposal for a Regulation of Digital Services Act Package, Ex Ante Regulatory Instrument for Large Online Platforms With Significant Network Effects Acting as Gatekeepers in the European Union’s Internal
Load more

Recommended publications
  • Integrating Preemption Threshold Scheduling and Dynamic Voltage Scaling for Energy Efficient Real-Time Systems
    Integrating Preemption Threshold Scheduling and Dynamic Voltage Scaling for Energy Efficient Real-Time Systems Ravindra Jejurikar1 and Rajesh Gupta2 1 Centre for Embedded Computer Systems, University of California Irvine, Irvine CA 92697, USA jeÞÞ@cec׺ÙciºedÙ 2 Department of Computer Science and Engineering, University of California San Diego, La Jolla, CA 92093, USA gÙÔØa@c׺Ùc×dºedÙ Abstract. Preemption threshold scheduling (PTS) enables designing scalable real-time systems. PTS not only decreases the run-time overhead of the system, but can also be used to decrease the number of threads and the memory require- ments of the system. In this paper, we combine preemption threshold scheduling with dynamic voltage scaling to enable energy efficient scheduling in real-time systems. We consider scheduling with task priorities defined by the Earliest Dead- line First (EDF) policy. We present an algorithm to compute threshold preemption levels for tasks with given static slowdown factors. The proposed algorithm im- proves upon known algorithms in terms of time complexity. Experimental results show that preemption threshold scheduling reduces on an average 90% context switches, even in the presence of task slowdown. Further, we describe a dynamic slack reclamation technique that working in conjunction with PTS that yields on an average 10% additional energy savings. 1 Introduction With increasing mobility and proliferation of embedded systems, low power consump- tion is an important aspect of embedded systems design. Generally speaking, the pro- cessor consumes a significant portion of the total energy, primarily due to increased computational demands. Scaling the processor frequency and voltage based on the per- formance requirements can lead to considerable energy savings.
    [Show full text]
  • What Is an Operating System III 2.1 Compnents II an Operating System
    Page 1 of 6 What is an Operating System III 2.1 Compnents II An operating system (OS) is software that manages computer hardware and software resources and provides common services for computer programs. The operating system is an essential component of the system software in a computer system. Application programs usually require an operating system to function. Memory management Among other things, a multiprogramming operating system kernel must be responsible for managing all system memory which is currently in use by programs. This ensures that a program does not interfere with memory already in use by another program. Since programs time share, each program must have independent access to memory. Cooperative memory management, used by many early operating systems, assumes that all programs make voluntary use of the kernel's memory manager, and do not exceed their allocated memory. This system of memory management is almost never seen any more, since programs often contain bugs which can cause them to exceed their allocated memory. If a program fails, it may cause memory used by one or more other programs to be affected or overwritten. Malicious programs or viruses may purposefully alter another program's memory, or may affect the operation of the operating system itself. With cooperative memory management, it takes only one misbehaved program to crash the system. Memory protection enables the kernel to limit a process' access to the computer's memory. Various methods of memory protection exist, including memory segmentation and paging. All methods require some level of hardware support (such as the 80286 MMU), which doesn't exist in all computers.
    [Show full text]
  • Chapter 1. Origins of Mac OS X
    1 Chapter 1. Origins of Mac OS X "Most ideas come from previous ideas." Alan Curtis Kay The Mac OS X operating system represents a rather successful coming together of paradigms, ideologies, and technologies that have often resisted each other in the past. A good example is the cordial relationship that exists between the command-line and graphical interfaces in Mac OS X. The system is a result of the trials and tribulations of Apple and NeXT, as well as their user and developer communities. Mac OS X exemplifies how a capable system can result from the direct or indirect efforts of corporations, academic and research communities, the Open Source and Free Software movements, and, of course, individuals. Apple has been around since 1976, and many accounts of its history have been told. If the story of Apple as a company is fascinating, so is the technical history of Apple's operating systems. In this chapter,[1] we will trace the history of Mac OS X, discussing several technologies whose confluence eventually led to the modern-day Apple operating system. [1] This book's accompanying web site (www.osxbook.com) provides a more detailed technical history of all of Apple's operating systems. 1 2 2 1 1.1. Apple's Quest for the[2] Operating System [2] Whereas the word "the" is used here to designate prominence and desirability, it is an interesting coincidence that "THE" was the name of a multiprogramming system described by Edsger W. Dijkstra in a 1968 paper. It was March 1988. The Macintosh had been around for four years.
    [Show full text]
  • A Hardware Preemptive Multitasking Mechanism Based on Scan-Path Register Structure for FPGA-Based Reconfigurable Systems
    A Hardware Preemptive Multitasking Mechanism Based on Scan-path Register Structure for FPGA-based Reconfigurable Systems S. Jovanovic, C. Tanougast and S. Weber Université Henri Poincaré, LIEN, 54506 Vandoeuvre lès Nancy, France [email protected] Abstract all the registers as well as all memories used in the circuit In this paper, we propose a hardware preemptive and to determine the starting point of the restoration multitasking mechanism which uses scan-path register process. On the other hand, the goal of the restoration is to structure and allows identifying the total task’s register restore the task’s context of processing as it was before its size for the FPGA-based reconfigurable systems. The interruption, in order to continue the execution previously main objective of this preemptive mechanism is to stopped. Several techniques allowing the hardware suspend hardware task having low priority, replace it by preemption are proposed in the literature. The pros and high-priority task and restart them at another time cons of mostly used approaches we will disscus in the (and/or from another area of the FPGA in FPGA-based following. designs). The main advantages of the proposed method The readback approach for context saving and storing are that it provides an attractive way for context saving of an outgoing task is one of the approaches which was and restoring of a hardware task without freezing other mostly used for the FPGA-based designs. No additional tasks during pre-emption phases and a small area hardware structures, simple implementation, no extra overhead. We show its feasibility by allowing us to design design efforts and no extra hardware consumption are the a simple computing example as well as the one of the most important advantages of this approach.
    [Show full text]
  • Preemptive Multitasking on Atmel® AVR® Microcontroller
    Advances in Information Science and Computer Engineering Preemptive Multitasking on Atmel® AVR® Microcontroller HABIBUR RAHMAN, Senthil Arumugam Muthukumaraswamy School of Engineering & Physical Sciences Heriot Watt University Dubai Campus Dubai International Academic City UNITED ARAB EMIRATES [email protected]; [email protected] Abstract: - This paper demonstrates the need for multitasking and scenario where multitasking is the only solution and how it can be achieved on an 8-bit AVR® microcontroller. This project explains how to create a simple kernel in a single C file, and execute any number of tasks in a multithreaded fashion. It first explains how the AVR® engine works and how it switches between different tasks using preemptive scheduling algorithm with the flexibility of blocking a task to allowing it more execution time based on their priority level. The code written for this project is basically in C, however the kernel code is mostly assembly functions called by C. The development environment is Atmel Studio®. The code is in such a way that it can be ported over any 8-bit AVR® microcontroller, however, this project demonstrates the results in both simulation and hardware chip on device Atmega8A. Key-Words: - AVR®, Microcontroller, Threading, Preemptive Scheduling, Multitasking. 1 Introduction architecture and will eventually lead to downloading Microcontroller development has been and compiling hundreds of files according to the exponential over the past two decades. Development provided operating system instructions and also in terms of speed, transistor density, multi-core spend time learning how to use it. embedding as well as number of peripheral subsystem on SoC(System on Chip) is common, and But if the user who has basic understanding of C development tools and compilers have been created language and very good understanding on that allows writing code for microcontroller on microcontroller wants to implement multitasking for higher level of abstraction layer an easy task.
    [Show full text]
  • UNIX History Page 1 Tuesday, December 10, 2002 7:02 PM
    UNIX History Page 1 Tuesday, December 10, 2002 7:02 PM CHAPTER 1 UNIX Evolution and Standardization This chapter introduces UNIX from a historical perspective, showing how the various UNIX versions have evolved over the years since the very first implementation in 1969 to the present day. The chapter also traces the history of the different attempts at standardization that have produced widely adopted standards such as POSIX and the Single UNIX Specification. The material presented here is not intended to document all of the UNIX variants, but rather describes the early UNIX implementations along with those companies and bodies that have had a major impact on the direction and evolution of UNIX. A Brief Walk through Time There are numerous events in the computer industry that have occurred since UNIX started life as a small project in Bell Labs in 1969. UNIX history has been largely influenced by Bell Labs’ Research Editions of UNIX, AT&T’s System V UNIX, Berkeley’s Software Distribution (BSD), and Sun Microsystems’ SunOS and Solaris operating systems. The following list shows the major events that have happened throughout the history of UNIX. Later sections describe some of these events in more detail. 1 UNIX History Page 2 Tuesday, December 10, 2002 7:02 PM 2 UNIX Filesystems—Evolution, Design, and Implementation 1969. Development on UNIX starts in AT&T’s Bell Labs. 1971. 1st Edition UNIX is released. 1973. 4th Edition UNIX is released. This is the first version of UNIX that had the kernel written in C. 1974. Ken Thompson and Dennis Ritchie publish their classic paper, “The UNIX Timesharing System” [RITC74].
    [Show full text]
  • Beyond Preemption:The Law and Policy of Intellectual Property
    Beyond Preemption:The Law and Policy of Intellectual Property Licensing Mark A. Lemley1† Table of Contents Introduction . I. The Tension Between Article 2B and Intellectual Property . A. Article 2B’s Expansion of the Scope and Power of Contracts . B. Potential Conflicts with Intellectual Property Law . 1. Patent Law . 2. Copyright Law . 3. Trade Secret Law . 4. Trademark Law . 5. Remedies . C. Conclusions . II. Preemption as a Partial Solution . A. The Nature of Intellectual Property Preemption . 1. The Basic Nature of Preemption . 2. Intellectual Property Preemption . a. Patent Law . b. Copyright Law . c. Applying Preemption to Contract Law . 1 Copyright © 1999 Mark A. Lemley and California Law Review, Inc. † Professor of Law, University of Texas School of Law; Visiting Professor of Law, Boalt Hall School of Law, University of California at Berkeley (Fall 1998); of counsel, Fish & Richardson P.C., Austin, Texas. I would like to thank Stephen Barnett, Julie Cohen, Richard Craswell, Robert Denicola, Rochelle Cooper Dreyfuss, Paul Goldstein, Robert Gomulkiewicz, Rose Hagan, Paul Heald, Dennis Karjala, Eric Lode, David McGowan, Charles McManis, Rob Merges, Maureen O’Rourke, Malla Pollack, Lloyd Weinreb, and participants in a faculty workshop at Stanford Law School and in the Berkeley Center for Law and Technology’s Conference on Article 2B of the Uniform Commercial Code for comments on an earlier draft. I would also like to thank Ryan Garcia and Sherri Shaw for research assistance. 111 CALIFORNIA LAW REVIEW [Vol. 87:111 B. The Limits of Preemption 1. Preemption Lacks Nuance . 2. Intellectual Property Rules Aren’t Always Statutory . 3. Intellectual Property Rules Aren’t Always Federal .
    [Show full text]
  • BIAS: Bluetooth Impersonation Attacks
    BIAS: Bluetooth Impersonation AttackS Daniele Antonioli Nils Ole Tippenhauer Kasper Rasmussen School of Computer and Communication Sciences CISPA Helmholtz Center Department of Computer Science EPFL for Information Security University of Oxford daniele.antonioli@epfl.ch [email protected] [email protected] Abstract—Bluetooth (BR/EDR) is a pervasive technology for subsequent secure connections. Two Bluetooth devices are wireless communication used by billions of devices. The Bluetooth expected to pair once and securely connect multiple times. standard includes a legacy authentication procedure and a secure During secure connection establishment the devices have to authentication procedure, allowing devices to authenticate to each other using a long term key. Those procedures are used authenticate the possession of the long term key that they have during pairing and secure connection establishment to prevent established while pairing. impersonation attacks. In this paper, we show that the Bluetooth In a recent paper, researchers showed that Bluetooth secure specification contains vulnerabilities enabling to perform imper- connection establishment is vulnerable to man-in-the-middle sonation attacks during secure connection establishment. Such attacks, even if the victims are already paired [4]. In that work vulnerabilities include the lack of mandatory mutual authenti- cation, overly permissive role switching, and an authentication however, the attack assumes that there is a legitimate secure procedure downgrade. We describe each vulnerability in detail, connection to break into. The attacker cannot target isolated and we exploit them to design, implement, and evaluate master Bluetooth devices, because the attacker cannot prove possession and slave impersonation attacks on both the legacy authentication of the victims’ long term key during secure connection procedure and the secure authentication procedure.
    [Show full text]
  • Precept 4: Multicore + Preemption
    Precept 4: Multicore + Preemption COS 318: Fall 2017 Project 4 Schedule ● Precept: Monday 11/6, 7:30pm ○ (You are here) ● Design Review: Monday 11/13 ● Due: Sunday, 11/19, 11:55pm Precept Overview ● Adding multicore support ● Preemption ● Producer-Consumer problem ● Project specific topics Multicore Support Supporting “SMP” ● SMP: Symmetric Multiprocessing ○ All CPUs have equivalent access to resources ● Bootup: BSP initializes system + activate APs ● Each CPU has a core and a LAPIC ○ LAPIC: Performs interrupt routing and delivery Stack organization ● Each processor needs its own kernel stack ○ Different from stacks used by process’s kernel threads ○ Location specified by processor’s TSS ● We use “kernel bootstrap stacks” ○ Switch to process kernel stack after performing setup Multiprocessor OS: CPU State ● Must distinguish between global state and per-CPU state ● What state is private to a CPU? Multiprocessor OS: Locking ● We can now have multiple CPUs in the kernel at the same time ○ What if they write to the same kernel memory? ● Strawman approach: Big Kernel Lock ● Our approach: Fine grained locking Preemptive Scheduling Preemption: Clock interrupts ● Current OS: One process can hog CPU ○ Want to preempt processes after a timeout ● On timer interrupt: forcefully switch to another thread ○ Allows interleaving without explicit yields Preemption: Scheduling ● LAPIC can give us timer interrupts ○ Count number of milliseconds thread has run for ○ Yield once runtime > threshold ● Choose another thread to run ○ We use round-robin Preempting Kernel Execution Which part will be affected? ● Temporarily enable interrupts during the executions of sys_produce and sys_consume ● Leave other parts of the kernel unchanged; ● So only enable interrupts during these two functions.
    [Show full text]
  • Multitasking and Real-Time Scheduling
    Multitasking and Real-time Scheduling EE8205: Embedded Computer Systems http://www.ee.ryerson.ca/~courses/ee8205/ Dr. Gul N. Khan http://www.ee.ryerson.ca/~gnkhan Electrical and Computer Engineering Ryerson University Overview • Processes/Tasks and Concurrency • Scheduling Priorities and Policies • Multitasking • Real-time Scheduling Fixed-Priority and Earliest Deadline First Scheduling • Sporadic and Aperiodic Process Scheduling Chapter 6 of the Text by Wayne Wolf, Chapter 13 of Text by Burns and Wellings © G. Khan Embedded Computer Systems–EE8205: Multitasking & Real-time Scheduling Page: 1 Introduction to Processes All multiprogramming operating systems are built around the concept of processes. Process is also called a task. OS and Processes • OS must interleave the execution of several processes to maximize CPU usage. Keeping reasonable/minimum response time • OS must allocate resources to processes. By avoiding deadlock • OS must also support: IPC: Inter-process communication Creation of processes by other processes © G. Khan Embedded Computer Systems–EE8205: Multitasking & Real-time Scheduling Page: 2 Task/Process Concept Serial Execution of Two Processes Interleaving the Execution of Process 1 and 2 © G. Khan Embedded Computer Systems–EE8205: Multitasking & Real-time Scheduling Page: 3 Processes and Managing Timing Complexity Multiple rates • multimedia • automotive Asynchronous Input • user interfaces • communication systems Engine Control Tasks Engine • spark control Controller • crankshaft sensing • fuel/air mixture • oxygen sensor • Kalman filter © G. Khan Embedded Computer Systems–EE8205: Multitasking & Real-time Scheduling Page: 4 Concurrency • Only one thread runs at a time while others are waiting. • Processor switches from one process to another so quickly that it appears all threads are running simultaneously.
    [Show full text]
  • COS 318: Operating Systems CPU Scheduling
    COS 318: Operating Systems CPU Scheduling Jaswinder Pal Singh Computer Science Department Princeton University (http://www.cs.princeton.edu/courses/cos318/) Today’s Topics u CPU scheduling basics u CPU scheduling algorithms 2 When to Schedule? u Process/thread creation u Process/thread exit u Process thread blocks (on I/O, synchronization) u Interrupt (I/O, clock) 3 Preemptive and Non-Preemptive Scheduling Terminate Exited (call scheduler) Scheduler dispatch Running Block for resource (call scheduler) Yield, Interrupt (call scheduler) Ready Blocked Create Resource free, I/O completion interrupt (move to ready queue) 4 Scheduling Criteria u Assumptions l One process per user and one thread per process l Processes are independent u Goals for batch and interactive systems l Provide fairness l Everyone makes some progress; no one starves l Maximize CPU utilization • Not including idle process l Maximize throughput • Operations/second (min overhead, max resource utilization) l Minimize turnaround time • Batch jobs: time to execute (from submission to completion) l Shorten response time • Interactive jobs: time response (e.g. typing on a keyboard) l Proportionality • Meets user’s expectations Scheduling Criteria u Questions: l What are the goals for PCs versus servers? l Average response time vs. throughput l Average response time vs. fairness Problem Cases u Completely blind about job types l Little overlap between CPU and I/O u Optimization involves favoring jobs of type “A” over “B” l Lots of A’s? B’s starve u Interactive process trapped
    [Show full text]
  • Contents of Lecture 8 on UNIX History
    Contents of Lecture 8 on UNIX History Before UNIX Origin of UNIX Commerical wars and other threats Linux Game over. UNIX won. Continued work by the original UNIX team: Plan 9 and Inferno Microkernels vs Monolithic kernels and other issues. Jonas Skeppstedt ([email protected]) Lecture 8 2014 1 / 67 CTSS The Compatible Time-Sharing System was designed at MIT in the early 1960s. Supported up to 32 simultanously logged in users: proof of the time-sharing idea. Ran on IBM 7090 with 32K 36 bit words, of which the monitor used 5K. User programs were swapped in from a magnetic drum (disk). Multilevel feedback scheduling queue. Higher priorities have shorter time quantum Initial priority (quantum) reflects size of the executable file so it can be swapped in and run. CTSS was extremely successful and used as late as 1972: basis for MULTICS. Jonas Skeppstedt ([email protected]) Lecture 8 2014 2 / 67 MULTICS Multiplexed Information and Computing Ser vice designed by MIT, AT&T, and GE. AT&T and GE provided telephone and electricity ser vices as utilities. GE also produced computers, eg the GE-645 used in MULTICS development. Why not do the same with computing power? The goal was one computer for 100,000s users in Boston (on hardware equivalent to about 386 or 486). Designed as an extension to CTSS with virtual memory and sophisticated protection (more levels than UNIX user vs superuser). MULTICS was written in PL/1 and consisted of about 300,000 lines. Jonas Skeppstedt ([email protected]) Lecture 8 2014 3 / 67 End of MULTICS Lots of people were very enthusiastic about MULTICS, including the newly graduated Ken Thompson from Berkeley.
    [Show full text]